[mcp-analysis] MCP Structural Analysis - 2026-03-26 #23094
Closed
Replies: 1 comment
-
|
This discussion was automatically closed because it expired on 2026-03-27T11:25:29.386Z.
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
10 tools analyzed today across 9 toolsets. Average usefulness rating 3.30/5.
list_discussionsandget_labelremain top performers;list_code_scanning_alertscontinues as the worst with ~137KB responses that overflow context. The actions toolset was tested today using the updatedactions_listmethod-based API (previouslylist_workflowsdirect tool — tool has been restructured).Full Structural Analysis Report
Executive Summary
Usefulness Ratings for Agentic Work
Schema Analysis
Response Size Analysis
Notable Observation: Actions Tool Restructured
The
list_workflowsstandalone tool no longer exists. It has been replaced bymcp__github__actions_listwithmethod: "list_workflows". Same behavior: per_page ignored, returns 30 items, 234 total workflows. The toolset is consistent but the API surface changed.30-Day Trend Summary
Recommendations
High-value tools (rating 4–5):
list_discussions,get_label,search_repositories,list_commits,list_issuesContext-efficient sweet spot (low tokens + high rating):
get_label(~25 tokens, 5/5),list_discussions(~100 tokens, 5/5),search_repositories(~125 tokens, 5/5)Tools needing improvement:
list_code_scanning_alerts— needs perPage support; currently context-breaking at scalelist_workflows— per_page parameter consistently ignored; returns 30 items regardlessget_file_contents— content returned in verbose resource wrapper; large files overwhelm contextAvoid calling
list_code_scanning_alertsinline — always persist to file or use filtering parameters if added.Visualizations
Response Size by Toolset
Usefulness Ratings
Daily Token Trend (Stacked by Toolset)
Size vs Usefulness
References: §23591527991
Beta Was this translation helpful? Give feedback.
All reactions